igneum-network/igneum
1
0
Fork 0
Code Issues Pull requests Releases Activity

Prover floor: the build recipe as it ran (Go pinned, the binary's sha256 and targets), the RISC Zero contingency figures with their source, playbook fixes

Browse source 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
igneum-labs 2026-10-05 22:33:31 +00:00
parent c0294eb6c5
commit 7ffae7b97a
3 changed files with 56 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
docs/analysis/prover-floor.md
View file

@ -89,3 +89,27 @@ upgrade repeats the clone, patch, build and measurement. The verifying key and t
(the patch changes buffer sizes and the shard split, not the circuits), which the `verify-segment` and `--mode
compressed` VERIFIED lines of the unpatched host show on every row below. The packaging path is a row for the
proving plan before 0.3.12, not this branch.
## Step 4 contingency, read not measured: RISC Zero's CUDA prover and its memory per segment
If SP1 could not be brought under 11 GB, the alternative's floor is read from its operators' documentation (not
measured here; a PC 2 run would be the measurement): Boundless' prover guide
(https://docs.boundless.network/provers/performance-optimization) sets the segment size cap by VRAM as 8 GB:
po2 19, 16 GB: po2 20, 20 GB: po2 21, 40 GB: po2 22, with measured peaks po2 20: 13,835 MiB, po2 21: 22,905 MiB,
po2 22: 41,089 MiB; RISC Zero's PR 3761 adds `low_vram` and `pinned_witgen` to fit po2 22 on a 24 GB 4090. So
RISC Zero proves a 2^19-cycle segment inside 8 GB and a 2^20 one inside 16 GB, and a shard of 4.7 M cycles is
9 segments at po2 19 plus lift and join steps (times not on the page). Adopting it would cost a second guest (the
chain rule in the RISC Zero zkVM), a second pinned program id, a second verifier in the node and no shared
aggregation between the two formats: `docs/analysis/amd-proving.md` and the proving plan carry that row already.
### The build, as it ran (job `floor-build-3`, 22:28:24 to 22:32:29Z)
Three runs: `floor-build-1` (22:17Z) and `floor-build-2` (22:24Z) failed in 2 to 4 minutes on
`crates/recursion/gnark-ffi/build.rs:70`, "Failed to build Go library: NotFound" (no `go` on PC 2; the first run's
playbook lost its own log, a bug fixed before the second). `floor-build-3` fetched go1.27.1 (tarball sha256
`63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445`, checked before unpacking under
`/opt/igneum-floor/go`, on the job's PATH only) and built in **240 s** (46 crates on the warm target of run 2, 8
niced jobs, 16 cores). The binary: `/opt/igneum-floor/bin/sp1-gpu-server`, **166,768,224 bytes, sha256
`5568108bf7fb9b0e525d8a08926b7046e51136ffaea53f0ca858631d0e938878`**, `--version` 6.8.1, `cuobjdump --list-elf`
sm_86, sm_89, sm_120 (the stock 251,306,680-byte server lists sm_80, 86, 89, 90, 100, 120 and compute_120 PTX).
The live `/root/.sp1/bin/sp1-gpu-server` (c2642ad1...) was never touched; the miners mined throughout.

21
tools/prover-floor/make-build-playbook.sh
View file

@ -41,21 +41,32 @@ echo "RESULT source \$(git describe --tags --always) \$(git rev-parse HEAD)"
git apply "\$PATCH" || { echo "RESULT build_failed patch does not apply"; exit 2; }
touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs
echo "RESULT patched \$(git diff --stat | tail -1)"
# Go, as the release workflow installs it (the server's native-gnark feature compiles the gnark library with go;
# the wrap path is never run by a compressed proof, but the feature is upstream's and stays): a pinned tarball
# unpacked under /opt/igneum-floor, on this job's PATH only, no package installed on the PC.
if ! command -v go >/dev/null 2>&1; then
sed -i 's/sp1-prover = { workspace = true, features = \["native-gnark"\] }/sp1-prover = { workspace = true }/' sp1-gpu/crates/server/Cargo.toml
echo "RESULT native_gnark dropped: no go toolchain on PC 2 (the gnark wrap is not used by compressed proofs)"
if [ ! -x \$FLOOR/go/bin/go ]; then
echo "STAGE go \$(stamp) fetching go1.27.1 (70,553,950 bytes, sha256 63d339f0...)"
curl -sSL -o \$FLOOR/go.tgz https://go.dev/dl/go1.27.1.linux-amd64.tar.gz || { echo "RESULT build_failed go download"; exit 2; }
echo "63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445 \$FLOOR/go.tgz" | sha256sum -c - >/dev/null || { echo "RESULT build_failed go sha256 mismatch: \$(sha256sum \$FLOOR/go.tgz)"; exit 2; }
echo "RESULT go_tarball sha256 \$(sha256sum \$FLOOR/go.tgz | cut -c1-64) matches 63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445"
tar -xzf \$FLOOR/go.tgz -C \$FLOOR && rm -f \$FLOOR/go.tgz
fi
export PATH="\$FLOOR/go/bin:\$PATH" GOPATH=\$FLOOR/gopath GOCACHE=\$FLOOR/gocache GOFLAGS=-mod=mod
fi
echo "RESULT go \$(go version 2>&1 | head -1)"
LOG=\$FLOOR/logs/build.log; : > "\$LOG"
echo "RESULT dirs \$(ls -ld \$FLOOR \$FLOOR/logs 2>&1 | tr '\\n' ' ') pwd=\$(pwd)"
export CUDA_ARCHS=86,89,120 CARGO_TARGET_DIR=\$FLOOR/target
JOBS=8
echo "STAGE build \$(stamp) jobs=\$JOBS"
t0=\$(date +%s)
nice -n 19 cargo build --release --bin sp1-gpu-server -j \$JOBS > \$FLOOR/logs/build-\$(date -u +%Y%m%dT%H%M%SZ).log 2>&1 &
nice -n 19 cargo build --release --bin sp1-gpu-server -j \$JOBS >> "\$LOG" 2>&1 &
BP=\$!
LOG=\$(ls -t \$FLOOR/logs/build-*.log | head -1)
while kill -0 \$BP 2>/dev/null; do sleep 120; echo "STAGE building \$(stamp) \$(( (\$(date +%s) - t0) / 60 )) min: \$(grep -c '^ Compiling' "\$LOG") crates compiled, last: \$(grep '^ Compiling' "\$LOG" | tail -1 | tr -s ' ' | cut -c1-80)"; done
wait \$BP; rc=\$?
echo "RESULT build_exit \$rc time_s=\$(( \$(date +%s) - t0 )) crates=\$(grep -c '^ Compiling' "\$LOG")"
if [ \$rc -ne 0 ]; then echo "RESULT build_failed"; grep -n -B2 -A12 '^error' "\$LOG" | head -80; exit 2; fi
if [ \$rc -ne 0 ]; then echo "RESULT build_failed"; echo "== error lines =="; grep -n -B2 -A12 -E '^(error|warning: unused manifest| process didn|caused by)' "\$LOG" | head -100; echo "== log tail =="; tail -n 60 "\$LOG"; exit 2; fi
BIN=\$FLOOR/target/release/sp1-gpu-server
cp "\$BIN" \$FLOOR/bin/sp1-gpu-server && cp "\$BIN" \$FLOOR/home/.sp1/bin/sp1-gpu-server && chmod +x \$FLOOR/bin/sp1-gpu-server \$FLOOR/home/.sp1/bin/sp1-gpu-server
echo "RESULT binary bytes=\$(stat -c %s "\$BIN") sha256=\$(sha256sum "\$BIN" | cut -c1-64) version=\$(\$BIN --version 2>/dev/null)"

21
tools/prover-floor/pc2-build-server.ps1
View file

@ -31,21 +31,32 @@ echo "RESULT source $(git describe --tags --always) $(git rev-parse HEAD)"
git apply "$PATCH" || { echo "RESULT build_failed patch does not apply"; exit 2; }
touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs
echo "RESULT patched $(git diff --stat | tail -1)"
# Go, as the release workflow installs it (the server's native-gnark feature compiles the gnark library with go;
# the wrap path is never run by a compressed proof, but the feature is upstream's and stays): a pinned tarball
# unpacked under /opt/igneum-floor, on this job's PATH only, no package installed on the PC.
if ! command -v go >/dev/null 2>&1; then
sed -i 's/sp1-prover = { workspace = true, features = \["native-gnark"\] }/sp1-prover = { workspace = true }/' sp1-gpu/crates/server/Cargo.toml
echo "RESULT native_gnark dropped: no go toolchain on PC 2 (the gnark wrap is not used by compressed proofs)"
if [ ! -x $FLOOR/go/bin/go ]; then
echo "STAGE go $(stamp) fetching go1.27.1 (70,553,950 bytes, sha256 63d339f0...)"
curl -sSL -o $FLOOR/go.tgz https://go.dev/dl/go1.27.1.linux-amd64.tar.gz || { echo "RESULT build_failed go download"; exit 2; }
echo "63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445 $FLOOR/go.tgz" | sha256sum -c - >/dev/null || { echo "RESULT build_failed go sha256 mismatch: $(sha256sum $FLOOR/go.tgz)"; exit 2; }
echo "RESULT go_tarball sha256 $(sha256sum $FLOOR/go.tgz | cut -c1-64) matches 63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445"
tar -xzf $FLOOR/go.tgz -C $FLOOR && rm -f $FLOOR/go.tgz
fi
export PATH="$FLOOR/go/bin:$PATH" GOPATH=$FLOOR/gopath GOCACHE=$FLOOR/gocache GOFLAGS=-mod=mod
fi
echo "RESULT go $(go version 2>&1 | head -1)"
LOG=$FLOOR/logs/build.log; : > "$LOG"
echo "RESULT dirs $(ls -ld $FLOOR $FLOOR/logs 2>&1 | tr '\n' ' ') pwd=$(pwd)"
export CUDA_ARCHS=86,89,120 CARGO_TARGET_DIR=$FLOOR/target
JOBS=8
echo "STAGE build $(stamp) jobs=$JOBS"
t0=$(date +%s)
nice -n 19 cargo build --release --bin sp1-gpu-server -j $JOBS > $FLOOR/logs/build-$(date -u +%Y%m%dT%H%M%SZ).log 2>&1 &
nice -n 19 cargo build --release --bin sp1-gpu-server -j $JOBS >> "$LOG" 2>&1 &
BP=$!
LOG=$(ls -t $FLOOR/logs/build-*.log | head -1)
while kill -0 $BP 2>/dev/null; do sleep 120; echo "STAGE building $(stamp) $(( ($(date +%s) - t0) / 60 )) min: $(grep -c '^ Compiling' "$LOG") crates compiled, last: $(grep '^ Compiling' "$LOG" | tail -1 | tr -s ' ' | cut -c1-80)"; done
wait $BP; rc=$?
echo "RESULT build_exit $rc time_s=$(( $(date +%s) - t0 )) crates=$(grep -c '^ Compiling' "$LOG")"
if [ $rc -ne 0 ]; then echo "RESULT build_failed"; grep -n -B2 -A12 '^error' "$LOG" | head -80; exit 2; fi
if [ $rc -ne 0 ]; then echo "RESULT build_failed"; echo "== error lines =="; grep -n -B2 -A12 -E '^(error|warning: unused manifest| process didn|caused by)' "$LOG" | head -100; echo "== log tail =="; tail -n 60 "$LOG"; exit 2; fi
BIN=$FLOOR/target/release/sp1-gpu-server
cp "$BIN" $FLOOR/bin/sp1-gpu-server && cp "$BIN" $FLOOR/home/.sp1/bin/sp1-gpu-server && chmod +x $FLOOR/bin/sp1-gpu-server $FLOOR/home/.sp1/bin/sp1-gpu-server
echo "RESULT binary bytes=$(stat -c %s "$BIN") sha256=$(sha256sum "$BIN" | cut -c1-64) version=$($BIN --version 2>/dev/null)"